Talk:AMD 10h

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia

Unnamed section[edit]

How about adding a section for rumors concerning K10? =(

This is all wrong[edit]

The K10 was going to be a completely new architecture that would sometimes appear as dual-core yet sometimes meld the two "cores" into one for extreme single-thread performance. K10 failed. What came out is K8 rev 10h. It is K8 for crissakes in almost every way, the architecture's just been bumped to four cores like it was bumped to two cores a while back.

Why is Wikipedia continuing with the delusion that AMD released some sort of next-generation chip? I love AMD, but the dream of K10 died and K8 has had no successor :( AMD's not lying about it. It's not covering it up or saying anything to the contrary. This article is just sentimental delusion. :'( —Preceding unsigned comment added by 207.38.195.47 (talk) 03:41, 3 July 2008 (UTC)[reply]

This is NOT K10[edit]

With "K8", AMD people refer to anything from the original Opteron to Magny Cours. K10 is Bulldozer according to several CVs of AMD engineers. Look into LinkedIn profiles. K10 = Bulldozer. Mitch Alsup just recently said the same in comp.arch. And Mitch Alsup wrote: "(Ahem) K10 is BullDozer, K8 is Opteron and follow-ons." Remember Hans de Vries' Barcelona core image with markup? He called it K8L. K10 is just so widely used since Barcelona that it's nearly impossible to revert that.

The K10 for Phenom came from 10h family name. The K10.5 for Phenom II was then derived from that. K10.5 was made up by enthusiasts. The closest thing to a core codename for the Phenom-class cores has been Greyhound (for Agena/Barcelona) and Greyhound+ (for Deneb/Shanghai). Even then I don't think that was an official, public codename.
By Taklan, 122.173.25.37 (talk) 12:45, 4 January 2011 (UTC)[reply]

I doubt about the report from The Inquirer[edit]

The Inquirer was famed to report misleading information in the industry. Many have proven that. Why delete the original introduction, according to the information that The Inquirer reported? I think that paragraph should be kept.

  • EDIT*: PLUS the article in the Inquirer was dated "Thursday 03 November 2005, 07:20". The article reported that the K10 was dead OR delayed, it was just mere speculation, and does not reflect the true status of the project in AMD. What we know is that K8L will be released between 1Q07-2Q08 (from the article), which will surely be staying in the market for a while (at least 18 months), but it doesn't mean that the K10 was dead, as K10's not even confirmed as K9.
  • EDIT 2*: reference to the Inquirer: Wiki Article about the site

202.71.240.18 10:06, 14 June 2006 (UTC)[reply]

The Inq is an interesting site for rumors, and they're occasionally correct. But rewriting an article around something they claim is extremely unwise. They are principally a rumor site, not a news site. Everything I've heard out of AMD leads me to believe K10 is going forward, and K9 is not. It's plausible K10 has been cancelled, and that kind of rumor is worthy of being briefly noted. Aluvus 12:22, 14 June 2006 (UTC)[reply]

As a beginning to an article, it has little relevance other than to just berate the'inq. We know how poor the reporting on the site can be for true reports, there is no need to re-iterate it here.

Something interesting...[edit]

TechReport: AMD outlines future technology directions. What will they make at that shiny new fab?

Something interesting on the ppt slide... "Future goals", should it be added to this article?

For the sentence below, I shall nominate this article for AfD.[edit]

According to this edit (revision ID: 71706208) from user Timharwoodx: "This would tend to confirm the claim that the original complex 8-issue K9 and K10 chip have been cancelled, and replaced with a multicore IPC enhanced Athlon 64 derivative."

With cited source from The Inquirer.

K10 are reported cancelled in the source, and now I'm convinced that K9 and K10 does not even exist at all. Thus this article and K9 (Yes, both articles) should be nominated for AfD, and redirected to AMD/K8L (Depends on the final discussion results).

I think that Timharwoodx should start writing an article about "a multicore IPC enhanced Athlon 64 derivative" though.

Anyone who wanted to prevent this page from deleted, should give users (at least me) proof of existence of the project (I don't care the type of the proof, or the codename of the project, just an official proof from AMD, not news reports and interviews from The Inquirer, DigiTimes, or any kind of "Tech Tabloid".). If no proof(s) given, then I'll go nominate this for AfD for the reason of "Non-existence" product based on speculations.

BTW, as K10 doesn't exist at all, I removed the future product tag. --202.71.240.18.

Article Cleanup Co-Ordination Point[edit]

It seems that K10 has never really been any more than a speculative code name for a future AMD microarchitecture. K9 "Greyhound" was discussed by a number of reliable sources in the time frame of 2003 to early 2004. But no reliable sources has ever divulged the name K10 as an actual microarchitectural design. The name K10 likely came by speculation in the industry based on PAST AMD naming conventions. After K9 cancelling in 2004, it is not likely that a product named K10 was actually in advanced stage of development, other than some vague discussion in the CV of former AMD employee named Andrew Glew that was picked up by The Inquirer http://www.theinquirer.net/inquirer/news/1008465/k10-architect-leaves-amd. Other bits of information in this article points to various times when AMD execs discussed future uarchitectures beyond K8, while providing no specific code name.

The chip we know as K8L (merely for convenient shorthand) may still be named K10, but there has been no robust evidence to that effect. Nor has the "New Mobile Microarchitecture" form AMD been indicated to adopt the K10 name. I think that we should keep most of the contents of the article, for some important historical information. Some of the technologies here are already in the process of being relized (such as chip level multiprocessing), some have proved to be impractical for the near to medium term (such as 10GHz frequency), while others have been refined (huge caches correspond well to possible use of Z-RAM technology). It's probably the best to eventually merge this article into K8L or "New Mobile Core from AMD" article, or if one of these proved to be code named K10, then do the reverse. Most of the information here are good and important as historical reference of the process of development in the industry, but non of it is really up to date any more.

--letowskie

This is NOT K10[edit]

With "K8", AMD people refer to anything from the original Opteron to Magny Cours. K10 is Bulldozer according to several CVs of AMD engineers. Look into LinkedIn profiles. K10 = Bulldozer. Mitch Alsup just recently said the same in comp.arch. And Mitch Alsup wrote: "(Ahem) K10 is BullDozer, K8 is Opteron and follow-ons." Remember Hans de Vries' Barcelona core image with markup? He called it K8L. K10 is just so widely used since Barcelona that it's nearly impossible to revert that.

The K10 for Phenom came from 10h family name. The K10.5 for Phenom II was then derived from that. K10.5 was made up by enthusiasts. The closest thing to a core codename for the Phenom-class cores has been Greyhound (for Agena/Barcelona) and Greyhound+ (for Deneb/Shanghai). Even then I don't think that was an official, public codename.
By Taklan, 122.173.25.37 (talk) 12:48, 4 January 2011 (UTC)[reply]

Phenom chips[edit]

Wow, the Phenom X2 chips come out in November! That's a while to wait. They must have delayed it. I heard they would come out in Q3, but this is Q4. Irdepesca572 08:12, 7 May 2007 (UTC)[reply]

No source quoted, not in the <ref> ones. --202.71.240.18 07:22, 8 May 2007 (UTC)[reply]

Inquirer news[edit]

http://theinquirer.net/default.aspx?article=39445

AM2+ will feature HT3 and DDR2 SDRAM at 1066 MHz while the successor of socket F will be socket G, not the so called socket F+, I think this need to be verified. --202.71.240.18 07:22, 8 May 2007 (UTC)[reply]

K10 Renamed 10h[edit]

According to this article, K10 is now known as AMD 10h. —The preceding unsigned comment was added by Irdepesca572 (talkcontribs) 16:45, 8 May 2007 (UTC).[reply]

The articles are named by its internal codename, so as K8 and K7 (AMD K9 being dual-core without much advertisments...), so just stick to K10, okay? --202.40.137.202 06:19, 9 May 2007 (UTC)[reply]
family 10h means 16, the "h" at end show it's hexadecimal, for comparison, Opteron is family 0Fh, the internal name is unknown, but probably K10. EduardoS 03:16, 13 May 2007 (UTC)[reply]

According to this article, the new microarchitecture is officially called Stars. Should we rename the article? Wafry (talk) 18:13, 19 November 2007 (UTC)[reply]

No Socket F+ (1207+), but socket G[edit]

Inq, I don't know if you guys think this is a credited source or not... Put it up if you like. --202.40.137.202 06:19, 9 May 2007 (UTC)[reply]

TLB bug was not mentioned[edit]

After the TLB bug has received some attention in the IT world I was a bit astonished to see no word of this phenomenon mentioned here. So I added a short chapter. --Bernd vdB (talk) 22:08, 6 February 2009 (UTC)[reply]

Why not rename the page to follow the real product name(s)?[edit]

Having been a Principal Member of the Technical Staff in AMD's central engineering organization from 12/2005 - 11/2008, I know the answers to a lot of these questions. Unfortunately the very nature of the information means that it is confidential and unverifiable -- that is why they call them code names. To make matters worse, it is common for companies to change the meaning of a code name in the middle of a project -- either by changing the project itself or by redirecting the code name to refer to a different project. Of course it is also common for companies to use another layer of code names internally, which may or may not bear any sustained correspondence with the code names that are sometimes used in public.

A logical way out of this mess is to name the pages for real products after the real product names.

In this case, I recommend renaming this page to AMD_Family10h (following the usage in AMD's BIOS and Kernel Developer's Guide) and removing any portions that do not pertain to the actual products. This would give contributors more confidence that they are updating the correct page.

To avoid this trouble in the future, I suggest that pages that have been created to discuss (possibly imaginary) unreleased products by their code names should be redirected or remain as no more than short stubs. If there is an overwhelming need for a page dedicated to unanounced future products, it should probably be named something like AMD_Future_Processors, so that at least the title would not become obsolete so quickly. John D. McCalpin, Ph.D. (talk) 22:16, 22 September 2009 (UTC)[reply]

  • Very valid points. Calling this K10 is a misnomer; the real K10 is Bulldozer. -Taklan, 122.173.25.37 (talk) 12:51, 4 January 2011 (UTC)[reply]

Unreliable thermal sensors?[edit]

According to the lm-sensors site the embedded sensors in some K10 processors are unreliable. lm-sensors has decided that there will never be support for K10 CPUs for this reason. "Family 10h CPU: Embedded sensors are known to be unreliable, and won't be supported ever." Maybe this should be included in the article. --216.254.228.94 (talk) 21:47, 7 October 2009 (UTC)[reply]

Update: the text has changed to "(2009-11-23) Embedded sensors are known to be unreliable on the DR-BA, DR-B2 and DR-B3 revisions of the family 10h CPU, which will never be supported. Work in progress by Jaswinder Singh Rajput and Clemens Ladisch. Needs review." --- So this applies to the Phenoms Agena and Toliman... and Athlon X2 Kuma, and whatever DR-BA was. --216.254.228.94 (talk) 18:46, 24 November 2009 (UTC)[reply]
Source: Revision Guide for AMD Family 10h Processors, Product Errata #319, page 22. --216.254.228.94 (talk) 19:36, 27 November 2009 (UTC)[reply]

AMD K10 rewrite[edit]

I started rewriting AMD K10 here User:Sasawat/K10 most of it is copy/pasted from the articles of AMD K10, AMD Phenom, Phenom II, AMD Athlon 64, Athlon 64 X2, Athlon II, and AMD Opteron

I believe that AMD K10 should give information about the microarchitecture, cores, and most importantly links to the pages with information of the actual processors themselves --SasawatThis Space For Rent 00:48, 12 October 2009 (UTC)[reply]

  • Please do consider my above responses in reference to the incorrect labeling of Greyhound-class/Stars cores as K10.
    By Taklan —Preceding unsigned comment added by 24.1.59.183 (talk) 18:45, 6 January 2011 (UTC)[reply]
  • I don't agree with the rewrite as that page is just summarizing Athlon II/Phenom/Phenom II and does not pertain to what the K10 article is actually about. This article is about the microarchitecture and not the CPU brand(s) themselves. That's what the individual Athlon II/Phenom/Phenom II pages are for. This is the same with the Intel Core pages, they're not about the microarchitecture, but the brand name. Same idea. -- cncxbox 01:46, 29 April 2011 (UTC).[reply]

Non-free file problems with File:AMD Phenom Logo.png[edit]

File:AMD Phenom Logo.png is non-free and has been identified as possibly not being in compliance with the non-free content policy. For specific information on the problems with the file and how they can be fixed, please check the message at File:AMD Phenom Logo.png. For further questions and comments, please use the non-free content review page. -- Toshio Yamaguchi 10:44, 9 July 2013 (UTC)[reply]

K10h :]][edit]

The "K10h" popped up in the Wikipedia too :D The WP says: (The "K10h" form that sometimes pops up is an improper hybrid of the "K" code and Family identifier number.) Is this a recursive definition or not, I cannot decide ... Pkunk (talk) 00:35, 6 February 2014 (UTC)[reply]

Llano-based Athlon II's[edit]

There are a few Llano-based Athlon II's (with a disabled IGP) as well, yet to be added to the list. Namely Athlon II X4 651/641/638/631. Perhaps there are more of it. — Preceding unsigned comment added by 80.99.178.153 (talk) 01:54, 11 May 2015 (UTC)[reply]

External links modified[edit]

Hello fellow Wikipedians,

I have just added archive links to 3 external links on AMD 10h. Please take a moment to review my edit. If necessary, add {{cbignore}} after the link to keep me from modifying it. Alternatively, you can add {{nobots|deny=InternetArchiveBot}} to keep me off the page altogether. I made the following changes:

When you have finished reviewing my changes, please set the checked parameter below to true to let others know.

checkY An editor has reviewed this edit and fixed any errors that were found.

  • If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
  • If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—cyberbot IITalk to my owner:Online 14:36, 12 January 2016 (UTC)[reply]

External links modified[edit]

Hello fellow Wikipedians,

I have just added archive links to 10 external links on AMD 10h. Please take a moment to review my edit. If necessary, add {{cbignore}} after the link to keep me from modifying it. Alternatively, you can add {{nobots|deny=InternetArchiveBot}} to keep me off the page altogether. I made the following changes:

When you have finished reviewing my changes, please set the checked parameter below to true to let others know.

checkY An editor has reviewed this edit and fixed any errors that were found.

  • If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
  • If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—cyberbot IITalk to my owner:Online 02:10, 14 February 2016 (UTC)[reply]

External links modified[edit]

Hello fellow Wikipedians,

I have just added archive links to one external link on AMD 10h. Please take a moment to review my edit. If necessary, add {{cbignore}} after the link to keep me from modifying it. Alternatively, you can add {{nobots|deny=InternetArchiveBot}} to keep me off the page altogether. I made the following changes:

When you have finished reviewing my changes, please set the checked parameter below to true or failed to let others know (documentation at {{Sourcecheck}}).

checkY An editor has reviewed this edit and fixed any errors that were found.

  • If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
  • If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—cyberbot IITalk to my owner:Online 11:37, 29 February 2016 (UTC)[reply]

External links modified[edit]

Hello fellow Wikipedians,

I have just modified one external link on AMD 10h. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:

When you have finished reviewing my changes, please set the checked parameter below to true or failed to let others know (documentation at {{Sourcecheck}}).

This message was posted before February 2018. After February 2018, "External links modified" talk page sections are no longer generated or monitored by InternetArchiveBot. No special action is required regarding these talk page notices, other than regular verification using the archive tool instructions below. Editors have permission to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the RfC before doing mass systematic removals. This message is updated dynamically through the template {{source check}} (last update: 18 January 2022).

  • If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
  • If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—InternetArchiveBot (Report bug) 05:50, 1 October 2016 (UTC)[reply]

External links modified[edit]

Hello fellow Wikipedians,

I have just modified 4 external links on AMD 10h. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:

When you have finished reviewing my changes, please set the checked parameter below to true or failed to let others know (documentation at {{Sourcecheck}}).

This message was posted before February 2018. After February 2018, "External links modified" talk page sections are no longer generated or monitored by InternetArchiveBot. No special action is required regarding these talk page notices, other than regular verification using the archive tool instructions below. Editors have permission to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the RfC before doing mass systematic removals. This message is updated dynamically through the template {{source check}} (last update: 18 January 2022).

  • If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
  • If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—InternetArchiveBot (Report bug) 11:48, 30 November 2016 (UTC)[reply]

External links modified[edit]

Hello fellow Wikipedians,

I have just modified 6 external links on AMD 10h. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:

When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.

This message was posted before February 2018. After February 2018, "External links modified" talk page sections are no longer generated or monitored by InternetArchiveBot. No special action is required regarding these talk page notices, other than regular verification using the archive tool instructions below. Editors have permission to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the RfC before doing mass systematic removals. This message is updated dynamically through the template {{source check}} (last update: 18 January 2022).

  • If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
  • If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—InternetArchiveBot (Report bug) 02:10, 24 June 2017 (UTC)[reply]

External links modified[edit]

Hello fellow Wikipedians,

I have just modified one external link on AMD 10h. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:

When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.

This message was posted before February 2018. After February 2018, "External links modified" talk page sections are no longer generated or monitored by InternetArchiveBot. No special action is required regarding these talk page notices, other than regular verification using the archive tool instructions below. Editors have permission to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the RfC before doing mass systematic removals. This message is updated dynamically through the template {{source check}} (last update: 18 January 2022).

  • If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
  • If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—InternetArchiveBot (Report bug) 22:41, 16 September 2017 (UTC)[reply]

Speculative information removed[edit]

I've commented out a large amount of information of the form the reported ship dates for the first Barcelona processors were set for September 10, 2007. This is speculation that would have fallen foul of WP:CRYSTAL at the time. Such information saying "X announced Y will be the case" is of vanishingly small historical interest. The implied statement "Y" (e.g. The first Barcelona processors shipped on September 10, 2007) is interesting, but without appropriate sources I can't change the statements into these verifiable historical forms.

I've also commented out the passage beginning Later processors were manufactured using 45 nm SOI technology, although this is in a historical form, because to make any sense it needs to be preceded by a historical statement about the 65 nm process used for earlier processors, but that information is likewise in speculative form. Hairy Dude (talk) 19:00, 4 January 2023 (UTC)[reply]